# WideResearch → MCP-Tasks

Calibration · https://benchgap.net/calibration/1687 · data retrieved 2026-10-29

MCP-Tasks is estimated from WideResearch with a Hill curve fitted on 5 models measured on both: y = 0.0000 + (1.1307 − 0.0000)·x^6.00 / (0.68509^6.00 + x^6.00), R² = 0.54, cross-validated error 6.0 pp. It is used for 5 estimates.

| Estimated model | WideResearch | MCP-Tasks | Source |
|---|---|---|---|
| [Atria Dawn Preview](https://benchgap.net/model/atria-dawn-preview.md) | 81.9% | 84.2% | estimated ± 6.0 pp, low confidence |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 81.9% | 84.2% | estimated ± 6.0 pp, low confidence |
| [Ornith-1.5-397B](https://benchgap.net/model/ornith-1-5-397b.md) | 80.8% | 82.4% | estimated ± 6.0 pp, low confidence |
| [dots3-note Preview](https://benchgap.net/model/dots3-note-preview.md) | 78.9% | 79.1% | estimated ± 6.0 pp, low confidence |
| [Ornith-1.5-35B-A3B](https://benchgap.net/model/ornith-1-5-35b-a3b.md) | 67.8% | 54.8% | estimated ± 6.0 pp, low confidence |

## Fitted on

| Model | WideResearch | MCP-Tasks |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 76.4% | 71.8% |
| [GLM-5](https://benchgap.net/model/glm-5.md) | 69.8% | 60.8% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 72.7% | 59.1% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 74.0% | 74.2% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 74.3% | 74.1% |